Delete network security group

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Adds substantial behavior beyond the annotations: required permissions (networking:manage, with the note that full/read defaults do not grant networking), backend-enforced ownership/feature/2FA locks, and that acceptance is pending rather than proof of connectivity. It also documents async polling semantics (in_progress/reason_kind/reason_code, next_check_seconds) and recovery guidance (reuse only the original idempotencyKey, never auto-retry).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core action and its precondition, then proceeds to permissions and operation-polling guidance. It is dense and long, but nearly every sentence carries operational instruction; the polling/error-handling sentences are the most verbose and could be tightened.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description compensates by explaining what is returned and how to interpret it (the returned operation/resource, its in_progress flag, next_check_seconds between reads, reason_kind failure as the only failure). For a destructive async delete with 4 required params, nothing essential is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 75%, and the description adds meaning for two parameters the schema only partially explains: expected_revision ('delete at its expected revision' implies optimistic concurrency) and idempotencyKey ('reuse only the original key and unchanged request'). group_id is characterized as an unreferenced customer group; project_id is not addressed in prose.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource (delete a network security group) and adds a scoping condition (only unreferenced groups; referenced ones are refused). This clearly separates it from siblings like update_network_security_group, clone_network_security_group, and create_network_security_group.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit preconditions: read current capabilities and owned resource state first, obtain approval for the exact change, and note that referenced groups are refused. It does not name a specific read-only sibling tool to call first, so it stops short of fully explicit tool routing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.